Safe Reinforcement Learning Using Robust Action Governor.

Yutong Li Nan Li H. Eric Tseng Anouck Girard Dimitar P. Filev Ilya V. Kolmanovsky

Published in: L4DC (2021)

Keyphrases

reinforcement learning
action selection
decision making
neural network
machine learning
learning algorithm
computer vision
case study
state space
sufficient conditions
mathematical model
model free
temporal difference
action space
partially observable domains